{"list":"other","total":55,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"2106.10199","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","created":"2021-06-18","cited_by_count":1245},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"1712.06584","title":"End-to-end Recovery of Human Shape and Pose","created":"2017-12-18","cited_by_count":885},{"id":"2103.00112","title":"Transformer in Transformer","created":"2021-02-27","cited_by_count":633},{"id":"1912.05656","title":"VIBE: Video Inference for Human Body Pose and Shape Estimation","created":"2019-12-11","cited_by_count":620},{"id":"1611.09813","title":"Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision","created":"2016-11-29","cited_by_count":494},{"id":"2102.04378","title":"TransReID: Transformer-based Object Re-Identification","created":"2021-02-08","cited_by_count":435},{"id":"1811.11742","title":"3D human pose estimation in video with temporal convolutions and semi-supervised training","created":"2018-11-28","cited_by_count":403},{"id":"1705.03098","title":"A simple yet effective baseline for 3d human pose estimation","created":"2017-05-08","cited_by_count":401},{"id":"2303.04803","title":"Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models","created":"2023-03-08","cited_by_count":375},{"id":"2103.10455","title":"3D Human Pose Estimation with Spatial and Temporal Transformers","created":"2021-03-18","cited_by_count":272},{"id":"2104.00272","title":"Mesh Graphormer","created":"2021-04-01","cited_by_count":265},{"id":"1904.03345","title":"Semantic Graph Convolutional Networks for 3D Human Pose Regression","created":"2019-04-06","cited_by_count":204},{"id":"1712.03453","title":"Single-Shot Multi-Person 3D Pose Estimation From Monocular RGB","created":"2017-12-09","cited_by_count":195},{"id":"2203.00859","title":"MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video","created":"2022-03-02","cited_by_count":159},{"id":"2111.12707","title":"MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation","created":"2021-11-24","cited_by_count":151},{"id":"1705.01583","title":"VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera","created":"2017-05-03","cited_by_count":129},{"id":"1704.00159","title":"Compositional Human Pose Regression","created":"2017-04-01","cited_by_count":124},{"id":"2004.03686","title":"Exemplar Fine-Tuning for 3D Human Model Fitting Towards In-the-Wild 3D Human Pose Estimation","created":"2020-04-07","cited_by_count":113},{"id":"2007.09389","title":"SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach","created":"2020-07-18","cited_by_count":94},{"id":"2105.02465","title":"PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation","created":"2021-05-06","cited_by_count":89},{"id":"1902.09868","title":"RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimation","created":"2019-02-26","cited_by_count":85},{"id":"2004.13985","title":"Motion Guided 3D Pose Estimation from Videos","created":"2020-04-29","cited_by_count":85},{"id":"2303.11579","title":"Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation","created":"2023-03-21","cited_by_count":82},{"id":"2006.07778","title":"Cascaded deep monocular 3D human pose estimation with evolutionary training data","created":"2020-06-14","cited_by_count":80},{"id":"2206.05253","title":"Rethinking Spatial Invariance of Convolutional Networks for Object Counting","created":"2022-06-10","cited_by_count":54},{"id":"2304.10465","title":"Implicit Temporal Modeling with Learnable Alignment for Video Recognition","created":"2023-04-20","cited_by_count":46},{"id":"1609.05317","title":"Deep Kinematic Pose Regression","created":"2016-09-17","cited_by_count":40},{"id":"2103.16449","title":"Bilevel Online Adaptation for Out-of-Domain Human Mesh Reconstruction","created":"2021-03-30","cited_by_count":39},{"id":"1607.02046","title":"MoCap-guided Data Augmentation for 3D Pose Estimation in the Wild","created":"2016-07-07","cited_by_count":37},{"id":"1909.07057","title":"Learning Spatial Awareness to Improve Crowd Counting","created":"2019-09-16","cited_by_count":36},{"id":"2211.09590","title":"Hypergraph Transformer for Skeleton-based Action Recognition","created":"2022-11-17","cited_by_count":36},{"id":"2007.02054","title":"Inference Stage Optimization for Cross-scenario 3D Human Pose Estimation","created":"2020-07-04","cited_by_count":35},{"id":"2007.11622","title":"TinyTL: Reduce Activations, Not Trainable Parameters for Efficient On-Device Learning","created":"2020-07-22","cited_by_count":32},{"id":"2112.11593","title":"AdaptPose: Cross-Dataset Adaptation for 3D Human Pose Estimation by Learnable Motion Generation","created":"2021-12-22","cited_by_count":32},{"id":"1702.02258","title":"Generating Multiple Diverse Hypotheses for Human 3D Pose Consistent with 2D Joint Detections","created":"2017-02-08","cited_by_count":30},{"id":"1811.04989","title":"OriNet: A Fully Convolutional Network for 3D Human Pose Estimation","created":"2018-11-12","cited_by_count":28},{"id":"1704.04886","title":"Multi-View Image Generation from a Single-View","created":"2017-04-17","cited_by_count":27},{"id":"1804.05287","title":"Video2Shop: Exact Matching Clothes in Videos to Online Shopping Images","created":"2018-04-14","cited_by_count":26},{"id":"2302.01825","title":"HDFormer: High-order Directed Transformer for 3D Human Pose Estimation","created":"2023-02-03","cited_by_count":23},{"id":"2208.08965","title":"GSRFormer: Grounded Situation Recognition Transformer with Alternate Semantic Attention Refinement","created":"2022-08-18","cited_by_count":20},{"id":"2303.16456","title":"Global Adaptation meets Local Generalization: Unsupervised Domain Adaptation for 3D Human Pose Estimation","created":"2023-03-29","cited_by_count":19},{"id":"1909.07608","title":"Improving the Learning of Multi-column Convolutional Neural Network for Crowd Counting","created":"2019-09-17","cited_by_count":15},{"id":"2207.13259","title":"Spatiotemporal Self-attention Modeling with Temporal Patch Shift for Action Recognition","created":"2022-07-27","cited_by_count":15},{"id":"2210.15511","title":"ProContEXT: Exploring Progressive Context Transformer for Tracking","created":"2022-10-27","cited_by_count":14},{"id":"2007.09077","title":"Generating Person Images with Appearance-aware Pose Stylizer","created":"2020-07-17","cited_by_count":13},{"id":"2303.17144","title":"DAMO-StreamNet: Optimizing Streaming Perception in Autonomous Driving","created":"2023-03-30","cited_by_count":13},{"id":"2210.15518","title":"LongShortNet: Exploring Temporal and Semantic Features Fusion in Streaming Perception","created":"2022-10-27","cited_by_count":12},{"id":"2305.11468","title":"Overcoming Topology Agnosticism: Enhancing Skeleton-Based Action Recognition through Redefined Skeletal Topology Awareness","created":"2023-05-19","cited_by_count":8},{"id":"2305.16437","title":"KeyPosS: Plug-and-Play Facial Landmark Detection through GPS-Inspired True-Range Multilateration","created":"2023-05-25","cited_by_count":3}],"next_cursor":null}